XIE Yining, HUANG Jinjie, HE Yongjun. One Dictionary vs. Two Dictionaries in Sparse Coding Based Denoising[J]. Chinese Journal of Electronics, 2017, 26(2): 367-371. doi: 10.1049/cje.2017.01.014
Citation: XIE Yining, HUANG Jinjie, HE Yongjun. One Dictionary vs. Two Dictionaries in Sparse Coding Based Denoising[J]. Chinese Journal of Electronics, 2017, 26(2): 367-371. doi: 10.1049/cje.2017.01.014

One Dictionary vs. Two Dictionaries in Sparse Coding Based Denoising

doi: 10.1049/cje.2017.01.014
Funds:  This work is supported by the National Natural Science Foundation of China (No.61305001, No.61673142), the Research Fund for the Doctoral Program of Higher Education of China (No.20132303120003).
  • Received Date: 2016-05-12
  • Rev Recd Date: 2016-10-28
  • Publish Date: 2017-03-10
  • As a promising technique, sparse coding can be widely used for representation, compression, denoising and separation of signals. This technique has been introduced into noisy speech processing, where enhancing speech itself or speech feature remains a challenge. Unlike other fields where noises are dense, the noises in speech are often sparse or partly sparse over the speech dictionary, resulting in performance degradation. It is necessary to understand the noise conditions of speech environments and the applied range of sparse coding. This paper analyzes the assumptions of sparse coding and provides the bounds of reconstruction error for two sparse coding methods which are widely used. Based on this analysis, the performance of the two methods under different conditions are compared. The results show that the performance of sparse coding can be improved by a well-prepared noise dictionary. Experiments on speech enhancement and recognition are conducted, and the results coincide with the theoretical analysis well.
  • loading
  • C.D. Sigg, T. Dikk and J.M. Buhmann, "Speech enhancement with sparse coding in learned dictionaries", Proc. ICASSP, Dallas, Texas, USA, pp.4758-4761, 2010.
    D.L. Donoho, "Compressed sensing", IEEE Trans. Inf. Theory, Vol.52, No.4, pp.1289-1306, 2006.
    D. Wu, W. Zhu and M.N.S. Swamy, "Compressive sensing-based speech enhancement in non-sparse noisy environments", IET Signal Processing, Vol.7, No.5, pp.450-457, 2013.
    D. Baby and H. Van hamme, "Supervised speech dereverberation in noisy environments using exemplar-based sparse representations", Proc. ICASSP, Shanghai, pp.156-160, 2016.
    D. You, J. Han, G. Zheng, et al., "Sparse power spectrum based robust voice activity detector", Proc. ICASSP, pp.289-292, 2012.
    W. Li, Y. Zhou, N. Poh, et al., "Feature denoising using joint sparse representation for in-car speech recognition", IEEE Signal Processing Letters, Vol.20, No.7, pp.681-684, 2013.
    J.F. Gemmeke, T. Virtanen and A. Hurmalainen, "Exemplar-based sparse representations for noise robust automatic speech recognition", IEEE Trans. on Audio, Speech, and Language Processing, Vol.19, No.7, pp.2067-2080, 2011.
    D.L. Donoho, M. Elad and V.N. Temlyakov, "Stable recovery of sparse overcomplete representations in the presence of noise", IEEE Trans. Inf. Theory, Vol.52, No.1, pp.6-18, 2006.
    J. Bobin, J.-L. Starck, J.M. Fadili, et al., "Morphological component analysis:An adaptive thresholding strategy", IEEE Trans. on Image Processing, Vol.16, No.11, pp.2675-2681, 2007.
    S. Chen, D. Donoho and M. Saunders, "Atomic decomposition by basis pursuit", SIAM Rev., Vol.43, No.1, pp.129-159, 2001.
    Y. Steve, E. Gunnar, G. Mark, et al., "HTK book", http://htk.eng.cam.ac.uk/docs/docs.shtml, 2015-04-12.
    L. Lamel, R. Kassel and S. Seneff, "Speech database development:design and analysis of the acoustic-phonetic corpus", Proc. of the DARPA Speech Recognition Workshop, pp.161-170, 1986.
    "NOISEX-92", available:http://www.speech.cs.cmu.edu/comp.spe-ech/Section1/Data/noisex.html, 1996-08-13.
    H. Hirsch and D. Pearce, "The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy con-ditions", Proc. ISCA Tutorial Research Workshop ASR2000, Paris, France, pp.181-188, 2000.
    D. Macho, L. Mauuary and B. Noe, "Evaluation of a noise-robust DSR front-end on Aurora databases", Proc. ICSLP, Denver, CO, pp.17-20, 2002.
  • 加载中


    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views (129) PDF downloads(410) Cited by()
    Proportional views


    DownLoad:  Full-Size Img  PowerPoint